Skip to main content

Zhenwen Dai: What Are the Invariant Occlusive Components of Image Patches? A Probabilistic Generative Approach

Movies Preview

movies
Zhenwen Dai: What Are the Invariant Occlusive Components of Image Patches? A Probabilistic Generative Approach


Published December 4, 2013


Talk by Zhenwen Dai, of the FIAS, Goethe University Frankfurt, Germany. Given to the Redwood Center for Theoretical Neuroscience at UC Berkeley.


Abstract
We study optimal image encoding based on a generative approach with non-linear feature combinations and explicit position encoding. By far most approaches to unsupervised learning of visual features, such as sparse coding or ICA, account for translations by representing the same features at different positions. Some earlier models used a separate encoding of features and their positions to facilitate invariant data encoding and recognition. All probabilistic generative models with explicit position encoding have so far assumed a linear superposition of components to encode image patches. Here, we for the first time apply a model with non-linear feature superposition and explicit position encoding for patches. By avoiding linear superpositions, the studied model represents a closer match to component occlusions which are ubiquitous in natural images. In order to account for occlusions, the non-linear model encodes patches qualitatively very different from linear models by using component representations separated into mask and feature parameters. We first investigated encodings learned by the model using artificial data with mutually occluding components. We find that the model extracts the components, and that it can correctly identify the occlusive components with the hidden variables of the model. On natural image patches, the model learns component masks and features for typical image components. By using reverse correlation, we estimate the receptive fields associated with the model’s hidden units. We find many Gabor-like or globular receptive fields as well as fields sensitive to more complex structures. Our results show that probabilistic models that capture occlusions and invariances can be trained efficiently on image patches, and that the resulting encoding represents an alternative model for the neural encoding of images in the primary visual cortex.


Audio/Visual sound, color

comment
Reviews

There are no reviews yet. Be the first one to write a review.
SIMILAR ITEMS (based on metadata)
Arxiv.org
texts
eye 33
favorite 0
comment 0
Source: http://arxiv.org/abs/1109.0758v1
Arxiv.org
texts
eye 20
favorite 0
comment 0
Source: http://arxiv.org/abs/1202.3130v1
Community Video
by Franklyn Monk
movies
eye 408
favorite 0
comment 0
Community Video
movies
eye 14
favorite 0
comment 0
Community Video
by DecisionDataBases
movies
eye 788
favorite 0
comment 0
Community Video
movies
eye 40
favorite 0
comment 0
Community Video
movies
eye 12
favorite 0
comment 0
Community Video
movies
eye 32
favorite 0
comment 0
Community Video
movies
eye 27
favorite 0
comment 0